Training in progress, step 9320, checkpoint
Browse files
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1657
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d01c6d33fd436546c493f28d69e4d7fb2b755190bb6181a5cb8d26102686a7ed
|
| 3 |
size 1657
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14709
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c1b22774eaa1f792e3b09e5bf2105340ef72d18ccde37b15a1bdfde000fdaf85
|
| 3 |
size 14709
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:48fbb0051f9a0f487769bf2bf8763866a6442ff023d9189a5277715dff9e1529
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 71.
|
| 6 |
"eval_steps": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -16766,6 +16766,24 @@
|
|
| 16766 |
"mean_token_accuracy": 0.6503713637590408,
|
| 16767 |
"num_tokens": 33954828.0,
|
| 16768 |
"step": 9310
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16769 |
}
|
| 16770 |
],
|
| 16771 |
"logging_steps": 5,
|
|
@@ -16785,7 +16803,7 @@
|
|
| 16785 |
"attributes": {}
|
| 16786 |
}
|
| 16787 |
},
|
| 16788 |
-
"total_flos": 1.
|
| 16789 |
"train_batch_size": 4,
|
| 16790 |
"trial_name": null,
|
| 16791 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 71.6923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 9320,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 16766 |
"mean_token_accuracy": 0.6503713637590408,
|
| 16767 |
"num_tokens": 33954828.0,
|
| 16768 |
"step": 9310
|
| 16769 |
+
},
|
| 16770 |
+
{
|
| 16771 |
+
"epoch": 71.65384615384616,
|
| 16772 |
+
"grad_norm": 0.0,
|
| 16773 |
+
"learning_rate": 3.4299999999999998e-06,
|
| 16774 |
+
"loss": 1.6752,
|
| 16775 |
+
"mean_token_accuracy": 0.6633023738861084,
|
| 16776 |
+
"num_tokens": 33973326.0,
|
| 16777 |
+
"step": 9315
|
| 16778 |
+
},
|
| 16779 |
+
{
|
| 16780 |
+
"epoch": 71.6923076923077,
|
| 16781 |
+
"grad_norm": 0.0,
|
| 16782 |
+
"learning_rate": 3.405e-06,
|
| 16783 |
+
"loss": 1.757,
|
| 16784 |
+
"mean_token_accuracy": 0.6501501977443696,
|
| 16785 |
+
"num_tokens": 33991262.0,
|
| 16786 |
+
"step": 9320
|
| 16787 |
}
|
| 16788 |
],
|
| 16789 |
"logging_steps": 5,
|
|
|
|
| 16803 |
"attributes": {}
|
| 16804 |
}
|
| 16805 |
},
|
| 16806 |
+
"total_flos": 1.7237192726922854e+18,
|
| 16807 |
"train_batch_size": 4,
|
| 16808 |
"trial_name": null,
|
| 16809 |
"trial_params": null
|